{"ID":2824789,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.22519","arxiv_id":"2512.22519","title":"Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry Grounding","abstract":"Recent Vision-Language-Action (VLA) models have made impressive progress toward general-purpose robotic manipulation by post-training large Vision-Language Models (VLMs) for action prediction. Yet most VLAs entangle perception and control in a monolithic pipeline optimized purely for action, which can erode language-conditioned grounding. In our real-world tabletop tests, policies over-grasp when the target is absent, are distracted by clutter, and overfit to background appearance. To address these issues, we propose OBEYED-VLA (OBject-centric and gEometrY groundED VLA), a framework that explicitly disentangles perceptual grounding from action reasoning. Instead of operating directly on raw RGB, OBEYED-VLA augments VLAs with a perception module that grounds multi-view inputs into task-conditioned, object-centric, and geometry-aware observations. This module includes a VLM-based object-centric grounding stage that selects task-relevant object regions across camera views, along with a complementary geometric grounding stage that emphasizes the 3D structure of these objects over their appearance. The resulting grounded views are then fed to a pretrained VLA policy, which we fine-tune exclusively on single-object demonstrations collected without environmental clutter or non-target objects. On a real-world UR10e tabletop setup, OBEYED-VLA substantially improves robustness over strong VLA baselines across four challenging regimes and multiple difficulty levels: distractor objects, absent-target rejection, background appearance changes, and cluttered manipulation of unseen objects. Ablation studies confirm that both semantic grounding and geometry-aware grounding are critical to these gains. Overall, the results indicate that making perception an explicit, object-centric component is an effective way to strengthen and generalize VLA-based robotic manipulation.","short_abstract":"Recent Vision-Language-Action (VLA) models have made impressive progress toward general-purpose robotic manipulation by post-training large Vision-Language Models (VLMs) for action prediction. Yet most VLAs entangle perception and control in a monolithic pipeline optimized purely for action, which can erode language-co...","url_abs":"https://arxiv.org/abs/2512.22519","url_pdf":"https://arxiv.org/pdf/2512.22519v2","authors":"[\"Khoa Vo\",\"Taisei Hanyu\",\"Yuki Ikebe\",\"Trong Thang Pham\",\"Nhat Chung\",\"Minh Nhat Vu\",\"Duy Nguyen Ho Minh\",\"Anh Nguyen\",\"Anthony Gunderman\",\"Chase Rainwater\",\"Ngan Le\"]","published":"2025-12-27T08:31:25Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Language Model\"]","has_code":false}